{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HVATW2FUWXQANYHQMPJYGUXQGS","short_pith_number":"pith:HVATW2FU","schema_version":"1.0","canonical_sha256":"3d413b68b4b5e006e0f063d38352f0348a3125d58d4a7a86cda6382f67e266e9","source":{"kind":"arxiv","id":"2410.03435","version":1},"attestation_state":"computed","paper":{"title":"A General Framework for Producing Interpretable Semantic Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony K. H. Tung, Jun Yu, Qiang Huang, Yiqun Sun, Yixuan Tang","submitted_at":"2024-10-04T13:51:19Z","abstract_excerpt":"Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of interpretability limits their use in tasks that demand transparency. Recent approaches have improved interpretability by leveraging domain-expert-crafted or LLM-generated questions, but these methods rely heavily on expert input or well-prompt design, which restricts their generalizability and ability to generate discriminative questions across a wide range of tasks. To address these challenges, we introduce \\algo{CQG-M"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.03435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T13:51:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"77143a8126aa52397fbe6f496553fe22e34f5b9841b2093039edca3d30536bc1","abstract_canon_sha256":"6a9d9ab3030b650cbb32d1346860afbebb49d547e465c7c98783a5fd4612db48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:01.075930Z","signature_b64":"xdIhYcMqZuyNK9yDiRgp7/YoBPEHuz6aHgmGmMzY/fzTQLtUC8/+8I9M3SODlmHlbgaWmx37AD9KJY5s6n6fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d413b68b4b5e006e0f063d38352f0348a3125d58d4a7a86cda6382f67e266e9","last_reissued_at":"2026-07-05T09:16:01.075444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:01.075444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Framework for Producing Interpretable Semantic Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anthony K. H. Tung, Jun Yu, Qiang Huang, Yiqun Sun, Yixuan Tang","submitted_at":"2024-10-04T13:51:19Z","abstract_excerpt":"Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of interpretability limits their use in tasks that demand transparency. Recent approaches have improved interpretability by leveraging domain-expert-crafted or LLM-generated questions, but these methods rely heavily on expert input or well-prompt design, which restricts their generalizability and ability to generate discriminative questions across a wide range of tasks. To address these challenges, we introduce \\algo{CQG-M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03435","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.03435/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.03435","created_at":"2026-07-05T09:16:01.075506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03435v1","created_at":"2026-07-05T09:16:01.075506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03435","created_at":"2026-07-05T09:16:01.075506+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVATW2FUWXQA","created_at":"2026-07-05T09:16:01.075506+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVATW2FUWXQANYHQ","created_at":"2026-07-05T09:16:01.075506+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVATW2FU","created_at":"2026-07-05T09:16:01.075506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.03080","citing_title":"Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS","json":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS.json","graph_json":"https://pith.science/api/pith-number/HVATW2FUWXQANYHQMPJYGUXQGS/graph.json","events_json":"https://pith.science/api/pith-number/HVATW2FUWXQANYHQMPJYGUXQGS/events.json","paper":"https://pith.science/paper/HVATW2FU"},"agent_actions":{"view_html":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS","download_json":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS.json","view_paper":"https://pith.science/paper/HVATW2FU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03435&json=true","fetch_graph":"https://pith.science/api/pith-number/HVATW2FUWXQANYHQMPJYGUXQGS/graph.json","fetch_events":"https://pith.science/api/pith-number/HVATW2FUWXQANYHQMPJYGUXQGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS/action/storage_attestation","attest_author":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS/action/author_attestation","sign_citation":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS/action/citation_signature","submit_replication":"https://pith.science/pith/HVATW2FUWXQANYHQMPJYGUXQGS/action/replication_record"}},"created_at":"2026-07-05T09:16:01.075506+00:00","updated_at":"2026-07-05T09:16:01.075506+00:00"}